A specialized multibaseline stereo technique for obstacle detection
Authors:
- T. WilliamsonTWT. Williamson
- C. ThorpeCTC. Thorpe
- 27 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 238-244
Abstract
This paper presents a multibaseline stereo technique specially suited to detecting obstacles. A method is described for weakly calibrating a set of multibaseline stereo cameras with high accuracy. This method is then used to tailor the stereo search space to the special case where the world in front of the cameras consists mainly of nearly horizontal planar surfaces (the ground), where we are interested in deviations from those planar surfaces (obstacles). The resulting disparity maps are presented and compared to the output of a traditional stereo algorithm Author(s) Williamson, T. Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA Thorpe, C.Keywords
This publication has 5 references indexed in Scilit:
- An integrated stereo-based approach to automatic vehicle guidance2002
- Weakly-calibrated stereo perception for rover navigation2002
- A pyramid-based front-end processor for dynamic vision applicationsProceedings of the IEEE, 2002
- A stereo machine for video-rate dense depth mapping and its new applications1996
- Stereo vision for planetary rovers: Stochastic modeling to near real-time implementationInternational Journal of Computer Vision, 1992